Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    statements about the characteristics or conditions of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynos
    -0.15
    ailles
    -0.15
    awner
    -0.15
    aminer
    -0.14
    ê·
    -0.14
    머ëĭĪ
    -0.14
    asca
    -0.14
    kiye
    -0.14
    ncpy
    -0.13
    áty
    -0.13
    POSITIVE LOGITS
     back
    0.26
     een
    0.26
     BACK
    0.25
     Back
    0.24
     Finally
    0.22
     Here
    0.20
     pleased
    0.20
     Now
    0.19
     finally
    0.19
     my
    0.18
    Act Density 0.359%

    No Known Activations